Eliminating Label Leakage in Tree-Based Vertical Federated Learning

TL;DR

This paper identifies a new label inference attack in tree-based vertical federated learning and proposes two defense mechanisms to effectively prevent label leakage, enhancing privacy without sacrificing model utility.

Contribution

It introduces ID2Graph, a novel attack method for label inference in tree-based VFL, and proposes Grafting-LDP and andID-LMID defenses to mitigate this vulnerability.

Findings

ID2Graph effectively infers labels in tree-based VFL.

Proposed defenses significantly reduce label leakage.

Defense methods maintain high model utility.

Abstract

Vertical federated learning (VFL) enables multiple parties with disjoint features of a common user set to train a machine learning model without sharing their private data. Tree-based models have become prevalent in VFL due to their interpretability and efficiency. However, the vulnerability of tree-based VFL has not been sufficiently investigated. In this study, we first introduce a novel label inference attack, ID2Graph, which utilizes the sets of record IDs assigned to each node (i.e., instance space)to deduce private training labels. ID2Graph attack generates a graph structure from training samples, extracts communities from the graph, and clusters the local dataset using community information. To counteract label leakage from the instance space, we propose two effective defense mechanisms, Grafting-LDP, which improves the utility of label differential privacy with post-processing, and andID-LMID, which focuses on mutual information regularization. Comprehensive experiments on various datasets reveal that ID2Graph presents significant risks to tree-based models such as RandomForest and XGBoost. Further evaluations of these benchmarks demonstrate that our defense methods effectively mitigate label leakage in such instances